ffmpeg-video-editor

• Outcome: Review
• Latest audit: Sep 10, 2026 · 7:35 AM UTC
• Version: 1.0.0

Overview

This is a straightforward FFmpeg command generator, but its default command templates can silently overwrite files and are unsafe for untrusted filenames or parameters.

Review generated commands before running them, especially when filenames or parameters come from someone else. Prefer removing -y, using unique output filenames, and rejecting paths or filter values containing shell metacharacters such as $(), backticks, quotes, semicolons, or newlines.

A.I.G

Vulnerability Patterns

• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

• Location: SKILL.md:11

Finding

Shell Command Injection Through Unsafely Interpolated User-Controlled Parameters

Content

View full analysis

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• YARA Signatures: Malware Match, Webshell Match, Cryptominer Match
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High

• Category: YARA Match
• Confidence: 80% confidence

Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md

---
name: FFmpeg Video Editor
description: Generate FFmpeg commands from natural language video editing requests - cut, trim, convert, compress, change aspect ratio, extract audio, and more.
---

# FFmpeg Video Editor

You are a video editing assistant that translates natural language requests into FFmpeg commands. When the user asks to edit a video, generate the correct FFmpeg command.

## How to Generate Commands

1. **Identify the operation** from the user's request
2. **Extract parameters** (input file, output file, timestamps, formats, etc.)
3. **Generate the FFmpeg command** using the patterns below
4. **If output fi

Hidden Instructions

High

• Category: Prompt Injection
• Confidence: 60% confidence

Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 388)May include surrounding context.

text

Here's the command to cut your video from 1:21 to 1:35:

​```bash
ffmpeg -y -hide_banner -i "video.mp4" -ss 00:01:21 -to 00:01:35 -c copy "video_trimmed.mp4"
​```

Hidden Instructions

High

• Category: Prompt Injection
• Confidence: 60% confidence

Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 390)May include surrounding context.

text

Here's the command to cut your video from 1:21 to 1:35:

​```bash
ffmpeg -y -hide_banner -i "video.mp4" -ss 00:01:21 -to 00:01:35 -c copy "video_trimmed.mp4"
​```

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill directs the agent to always include FFmpeg's -y overwrite flag, which suppresses confirmation prompts and can silently replace existing files. In a skill that generates commands from user language, this increases the chance of accidental data loss if the output path collides with an existing file or if a user-supplied filename is reused.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.